Recommenders

Timetable

DayTimeFrequencyPeriodRoomLecturerRemarksMax. participants
Vorlesung(V) - Lecture - Dates/Times/Location:
Tue. 11:00 bis 13:00 weekly 09.04.2024 to
09.07.2024
G29-307 (Verwaltung durch FIN) Spiliopoulou   160
Übung (Ü) - Exercise - Dates/Times/Location: Group 1
Tue.13:00 bis 15:00weekly09.04.2024 to
09.07.2024
G22A-105 (40 Pl.) Tutor  30
Übung (Ü) - Exercise - Dates/Times/Location: Group 2
Thu.11:00 bis 13:00weekly11.04.2024 to
11.07.2024
G22A-105 (40 Pl.) Schleicher

Sprache: deutsch!

30
Übung (Ü) - Exercise - Dates/Times/Location: Group 3
Thu.15:00 bis 17:00weekly11.04.2024 to
11.07.2024
G22A-013 (70 Pl.) Schleicher  30
Übung (Ü) - Exercise - Dates/Times/Location: Group 4
Tue.13:00 bis 15:00weekly30.04.2024 to
09.07.2024
G22A-203 (40 Pl.) Tutor  30

Overview (from LSF)

Learning Content

Outline of the course:

The course consists of four blocks.

Block 1 delivers basics on how a recommender works and how it should be evaluated on historical data.

Block 2 is on methods for content-based recommendations; these methods suggest to a user an item on the basis of its similarity to items that the user has liked in the past.

Block 3 is on methods for neighbourhood-based recommendations; these methods suggest to a user an item on the basis of similarity between the preferences of this user and the preferences of other users. Blocks 2 and 3 contain also evaluation units; these describe methods for the experimental evaluation of recommenders under controlled conditions.

Block 4 contains a choice of special topics on recommenders, such as frameworks for the formulation of recommendation explanations.

Comments

Recommended background
Bachelor students: You should have completed the compulsory CS courses of the early semesters.

All students: Having attended data mining or machine learning or an AI course is of advantage, although you may catch up with home reading. You must refresh your secondary school background in statistics.

Description

Subject of this course is the recommendation engine / recommender, an instrument for the formulation of suggestions towards a user. These suggestions concern products to purchase, texts to read, videos to watch, or more general, items to obtain. A recommender has a front-end, responsible for the interaction between human and machine, and a back-end, responsible for learning and adaption of the machine's intelligent core.

 

Goals of the course:

  • Students understand how a recommender learns, why its model must be adapted and how
  • Students become familiar with a choice of recommender learning methods
  • Students understand how to evaluate a recommender

 

 

Literature

The main book of the RECSYS course is the 'Recommender Systems Handbook':

  • Recommender Systems Handbook by Francesco Ricci, Lior Rokach and Bracha Shapira (editors), SPRINGER (2015), 2nd edition, https://doi.org/10.1007/978-1-4899-7637-6
  • Recommender Systems Handbook by Francesco Ricci, Lior Rokach and Bracha Shapira (editors), SPRINGER (2022), 3rd edition, https://doi.org/10.1007/978-1-0716-2197-4

It is noted that the chapters in the 2015 edition are enumerated, while the chapters in the 2022 edition are not and are therefore cited only by title.

Further cited literature, including scientific articles and use cases are cited at the beginning of each unit.

Remarks

Exam

The course RECSYS can be examined for 5 ECTS or for 6 ECTS.

RECSYS-5ects

To acquire the 5 ECTS, enroll for the 5-ECTS-exam.

RECSYS-6ects

For the 6th credit point, you make an additional assignment which involves homework. There are two options for this assignment:

  • Option DEFAULT: You read one-two designated scientific papers discussed in class for Part IV. The titles of these papers will be announced in class, when Part IV starts. In the exam, you must answer arbitrary additional questions on this/these paper(s).
  • Option CHOICE: You read one scientific paper from a choice of papers on Part IV, make an in-class presentation on specific questions for this paper, and compile a short report on  the paper, including the answers you presented and the feedback you received. The titles of the papers offered for this option will be announced and distributed in class, when Part IV starts. During the exam, you are called to answer to a choice of the questions from the report you wrote. You can select Option CHOICE only in person, during the Meeting at which the papers are offered (most likely Meeting 10).

For the 6th credit point, Option DEFAULT is assumed for all students who did not actively select Option CHOICE, including those that started with the CHOICE assignment but did not finish it.  

Examination modalities

The RECSYS exam is oral by default. Depending on the number of students attending the course, it may be turned to a written exam (as usual for many FIN courses).

  • Written exam: RECSYS-5ects and RECSYS-6ects take place at the same time and have the same duration (120 min). If you have opted for CHOICE under RECSYS-6ects, you may still ask for the DEFAULT exam sheet. Make sure that you get the correct exam sheet, because no changes are permitted after you got an exam sheet.
  • Oral exam: make clear whether you take the exam for RECSYS-5ects or for RECSYS-6ects. If you have opted for CHOICE under RECSYS-6ects, you may still decide the option DEFAULT:  you must do so before the examination begins.
Prerequisites

None.

Target Group

RECSYS is for bachelor students in high semesters and for master students, as follows:

  • 5 ECTS: Bachelor INF, INGINF, CV and Bachelor WIF
  • 6 ECTS (additional materials): Master INF, INGINF, WIF, DigiEng, Data Science Master DKE

The exercise class for the bachelor degrees is on German, for the master degrees on English.

Under Exam you find additional information on how you acquire the 5 ECTS, resp. 6 ECTS

 

Description Recommenders

 

Letzte Änderung: 27.08.2024 - Ansprechpartner: